Cover Image

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bennion, Jonathan, Ghosh, Shaona, Singh, Mantek, Dziri, Nouha
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT?
by: Sun, Yiyou, et al.
Published: (2025)

The Geometries of Truth Are Orthogonal Across Tasks
by: Azizian, Waiss, et al.
Published: (2025)

TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities
by: Graf, Victoria, et al.
Published: (2026)

Statistical Comparative Analysis of Semantic Similarities and Model Transferability Across Datasets for Short Answer Grading
by: Bonthu, Sridevi, et al.
Published: (2025)

Towards Inference-time Category-wise Safety Steering for Large Language Models
by: Bhattacharjee, Amrita, et al.
Published: (2024)

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
by: Shen, Yiran, et al.
Published: (2025)

Why Do Safety Guardrails Degrade Across Languages?
by: Zhang, Max, et al.
Published: (2026)

Multilingual Prompt Engineering in Large Language Models: A Survey Across NLP Tasks
by: Vatsal, Shubham, et al.
Published: (2025)

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
by: Yang, Junxiao, et al.
Published: (2026)

OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities
by: Verma, Sahil, et al.
Published: (2025)

Noise Injection Systemically Degrades Large Language Model Safety Guardrails
by: Shahani, Prithviraj Singh, et al.
Published: (2025)

The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
by: Pan, Wenbo, et al.
Published: (2025)

Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
by: Yang, Ziyu, et al.
Published: (2026)

An Empirical Comparison of Text Summarization: A Multi-Dimensional Evaluation of Large Language Models
by: Janakiraman, Anantharaman, et al.
Published: (2025)

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
by: Ren, Richard, et al.
Published: (2024)

Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
by: Zhang, Haobo, et al.
Published: (2025)

CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias
by: Gupta, Vipul, et al.
Published: (2023)

ASAG2024: A Combined Benchmark for Short Answer Grading
by: Meyer, Gérôme, et al.
Published: (2024)

Can Safety Emerge from Weak Supervision? A Systematic Analysis of Small Language Models
by: Saha, Punyajoy, et al.
Published: (2026)

AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
by: Ghosh, Shaona, et al.
Published: (2024)

HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
by: Liu, Emmy, et al.
Published: (2026)

Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications
by: Balne, Charith Chandra Sai, et al.
Published: (2024)

Hierarchical Orthogonal Residual Spread for Precise Massive Editing in Large Language Models
by: Gu, Xiaojie, et al.
Published: (2026)

Orthogonal Finetuning for Direct Preference Optimization
by: Yang, Chenxu, et al.
Published: (2024)

Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropy
by: Penny-Dimri, Jahan C., et al.
Published: (2025)

CRACQ: A Multi-Dimensional Approach To Automated Document Assessment
by: Soltani, Ishak, et al.
Published: (2025)

Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement
by: Zhong, Qimin, et al.
Published: (2026)

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
by: Ramesh, Shyam Sundhar, et al.
Published: (2026)

PoPE: Legendre Orthogonal Polynomials Based Position Encoding for Large Language Models
by: Aggarwal, Arpit
Published: (2024)

A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
by: Luo, Kairong, et al.
Published: (2025)

SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
by: Li, Lijun, et al.
Published: (2024)

ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation
by: Liu, Qin, et al.
Published: (2025)

ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment
by: Naous, Tarek, et al.
Published: (2023)

TDBench: A Benchmark for Top-Down Image Understanding with Reliability Analysis of Vision-Language Models
by: Hou, Kaiyuan, et al.
Published: (2025)

IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning
by: Joshi, Abhinav, et al.
Published: (2024)

Reparameterized LLM Training via Orthogonal Equivalence Transformation
by: Qiu, Zeju, et al.
Published: (2025)

Identifying Intervenable and Interpretable Features via Orthogonality Regularization
by: Miller, Moritz, et al.
Published: (2026)

LOLgorithm: Integrating Semantic,Syntactic and Contextual Elements for Humor Classification
by: Khurana, Tanisha, et al.
Published: (2024)

Benchmarking Benchmark Leakage in Large Language Models
by: Xu, Ruijie, et al.
Published: (2024)

Benchmarking the Energy Savings with Speculative Decoding Strategies
by: Dutta, Rohit, et al.
Published: (2026)